Exploring Large Language Models for Collaborative Scenario Development in Simulation-Based Military Training

Exploring Large Language Models for Collaborative Scenario Development in Simulation-Based Military Training

연구 분야: Software Development

학회: International Conference on Human-Computer Interaction

This study explores the role of Large Language Models (LLMs) in the context of human-AI collaborative scenario development for military simulation-based training. We propose a conceptual framework that organizes scenario development into three key phases, supported by a sequence of LLM modules: from defining a training design and creating a conceptual scenario, to generating a scenario specification for execution in simulation. The approach supports the integration of external domain-specific knowledge sources, such as trainee qualification profiles, to ensure scenarios adhere to organization-specific training principles. Using a case study of helicopter pilot training, we evaluate how LLMs can enhance the efficiency and effectiveness of scenario development compared to traditional methods. Our findings highlight the promise of LLMs in streamlining scenario development workflows while maintaining instructional integrity.